Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations: it discloses that saving replaces the board's single art direction while the previous one stays in the library, that text naming a board item is refused, and that validation problems require a re-call. These are exactly the non-obvious behavioral traits (replacement semantics, refusal rules, error handling) an agent needs and that annotations do not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but front-loaded: trigger, write instruction, save semantics, content rules, and follow-up steps in a logical order. A few clauses (e.g. repeating the same-turn save and the brief pointer) are slightly verbose, though each still carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter, 9-required mutation tool with no output schema, the description covers purpose, trigger, content constraints, replacement behavior, and post-call handling. An agent has enough to invoke it correctly and recover from the validation responses it should expect.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: 'Fill every section with concrete, photographable choices', the rule that the direction names no garment/outfit/Model/Location, and that variations apply 'only when the user wants variety'. These are semantic constraints beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('create, write or save an art direction') and distinguishes itself from siblings by naming the exact situation (the board's New art direction) that triggers it. An agent can separate it from get_art_direction, list_art_directions and update_brief without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly gives when-to-use ('when the user asks...or the board's New art direction asks for one'), the alternative workflow ('If the board has a brief, apply it with update_brief direction.art_direction_id'), and the retry rule ('If the result lists problems, fix them all and call again'). Nothing is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.